臺灣博碩士論文加值系統

隨著網際網路的快速發展與數位影像科技的進步，日常生活中不斷有大量的影像資料被產生，而要管理這些大量的數位影像資料，必須透過精確與快速的搜尋方法，才能讓使用者能很方便且迅速地搜尋出自己所想要的影像資料。本論文的目的在發展出一個有效且快速的影像查詢系統。

在目前的影像查詢方法中，以影像內容為主(content-based image retrieval, CBIR)的影像查詢方法最廣受推崇。本論文結合K-means演算法(K-means cluster algorithm)和高斯馬可夫隨機場模型(Gaussian Markov Random Field Model)技術提出一影像特徵(feature)，以描述一影像之顏色(Color)與紋理(Texture)的特性，
本論文並利用此影像特徵建構一影像查詢系統。本論文同時也採用基因演算法(Genetic algorithm)，來決定該系統中所採用的權重(weights)參數。且使用實驗來驗證該演算法所獲得之權重參數的正確度，與該系統在執行時間上與查詢正確率上的效率。

With the rapid advancement of digital image and the Internet technology, a huge number of digital images are produced every moment. Therefore, developing an efficient and effective image retrieval system to cope with the image data is necessary. The purpose of this paper is to provide an image retrieval system so as to assist users in retrieving the desired images instantly and effectively.

Content-based image retrieval systems search for images similar to the query image from a given image database. As the use of image data is widely spread within many application domains, the efficient retrieval of voluminous and complex information, which is the intrinsic characteristic of multimedia data, is becoming increasingly important. This thesis integrates K-means algorithm and Gaussian Markov Random Field Model to offer a feature which can describe the texture and color distributions of an image. This thesis still develops an image retrieval system based on the feature and employs genetic algorithm to decide the weight parameters in this system. Besides, this thesis will investigate the performance of the system and the fitness of the weights obtained by genetic algorithm by experiments.

誌 謝 I
摘 要 II
Abstract III
目 錄 IV
表格目錄 V
圖目錄 VI
第一章、緒論 1
1.1 研究動機 5
1.2 研究目的 6
1.3 研究架構 7
第二章、文獻探討 8
2.1 顏色特徵值與K-Means分群演算法 8
2.2 模糊顏色直方圖(Fuzzy Color Histogram) 11
2.3 以區域顏色特徵值之影像查詢方法 15
2.4 高斯馬可夫隨機場模型 17
2.5 以紋理特徵值之影像查詢方法 19
2.6 基因演算法 21
第三章、Color-Texture Based Image Retrieval Method 28
3.1 影像特徵抽取 28
3.2 相似度計算 30
3.3 實驗結果 31
3.4 實驗討論 49
第四章、植基於基因演算法之特徵值參數最佳解法 51
4.1 實驗方法 51
4.2 實驗結果 54
第五章、結論與未來工作 59
5.1 結論 59
5.2 未來工作 61
參考文獻 62

[1]C. C. Chang, and Y. K. Chang (2000), “A Fast Filter for Image Retrieval Based on Color-Spatial Features,” SEMA2000, Baden-Baden, German, pp.47-51.
[2]Rui, Y. et al. “Image Retrieval: Current Techniques, Promising Directions and Open Issues,” J. Vis. Commun. Image Represent. 10, pp. 39-62.
[3]Swain, M., and Ballard, D. “Color indexing,” Int. J. Comput. Vis. 7, pp.11–32.
[4]Li, X. L., Tao, D. C., Yuan, Y., Yu, N. H., Liu, Z. K., and Tang, X. O., Illumination-Invariant Color Histogram Spectrum Feature for Content-Based Image Retrieval,” In IEEE Internat. Conf. Methods & Models in Automation & Robotics, pp. 555–559, 2002..
[5]B. M. Mehtre, M. S. KanKanhalli, and W. F. Lee(1998), “Content-Based Image Retrieval Using A Composite Color-Shape Approach,” Information Processing & Management, Vol. 34,No.1, pp. 109-120.
[6]J. Krumm, and S. A. Shafer(1995), ”Texture segmentation and shape in the same image,” The Fifth International Conference on Computer Vision, Cambridge, MA, USA, Vol. 1, pp. 121-127.
[7]M. S. Kankanhalli, B. M. Mehtre, and H. Y. Huang (2001), “Color And Spatial Feature for Content-Based Image Retrieval,” Pattern Recognition,Vol. 22, No. 3, pp. 323-337.
[8]R. Brunelli, and O. Mich (2001), “Histograms Analysis for Image Retrieval,” Pattern Recognition, Vol. 34, No. 8, pp. 1625-1637.
[9]J. M. Fuertes, M. Lucena, N. Pérez de la Blanca, and J. Chamorro-Martínez (2001), “A Scheme of Colour Image Retrieval from Databases,” Pattern Recognition, Vol. 22, No.3, pp. 323-337.
[10]Plataniotis, K.N., Venetsanopoulos, A.N., 2000. Color image processing and applications. Berlin, pp. 25–35.
[11]Haralick RM, Shanmugam, Dinstein I. Textural features for image classification. IEEETrans Syst,Man, Cybernetics 1973; SMC-3:610- 621.
[12]M. J. Swain, and D. H. Ballard (1991), “Color Indexing,” International Journal of Computer Vision, Vol. 7, No. 1, pp. 11-32.
[13]J. Han, and K.K. Ma (2002), “Fuzzy Color Histogram and Its Use in Color Image Retrieval”, IEEE transactions on Image Processing, Vol. 11, No. 8, pp 944-952.
[14]J. C. Bezdek (1981), “Pattern Recognition with Fuzzy Objective Function Algorithms”, Plenum, New York
[15]B. Hill, T. Roger, and F. W. Vorhagen (1997), “Comparative analysis of the quantization of Color spaces on the basis of the CIELAB Color-difference formula”, ACM Trans. Graph., Vol. 16, no. 2, pp 109-154.
[16]J.C. Dunn (1974), “A fuzzy relative of the ISODATA process and its use in Detecting compact, well separated clusters”, J. Cybernet 3, pp32-57.
[17]K. Vu, K. A. Hua, and W. Tavanapong, “Image Retrieval Based on Regions of Interest,” IEEE Transactions on Knowledge and Data Engineering, Vol. 15, No. 4, July/August 2003, PP. 1045-1049.
[18]K. A. Hua, K. Vu, and J. H. Oh, “Sammatch: A Flexible and Efficient Sampling-Based Image Retrieval Technique for Large Image Database,” The Proceedings of ACM International Conferences on Multimedia, pp. 225-234, October 1999.
[19]M. C. Su, and C. H. Chou (2001), “A Modified Version of the K-Means Algorithm with a Distance Based on Cluster Symmetry,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No.6, pp. 674-680.
[20]W. J. Kou (2001), “Study on Image Retrieval and Ultrasonic Diagnosis of Breast Tumors,” Ph.D. Dissertation, Department of Computer Science and Information Engineering, National Chung Cheng University, Taiwan, R.O.C., Chiayi.
[21]J. E. Besag, “Spatial interaction and the statistical analysis of lattice systems (with discussion),” J. R. Statist. Soc. B, vol. 36, no. 2, pp. 192–236,1974.
[22]H. Wang, “Compressed-domain image search and applications”, TR Columbia Univ., 1996.
[23]J. R. Smith and S.F. Chang, “Automated image retrieval using color and texture” TR Columbia Univ. 1996.
[24]R. Chellappa and S. Chatterjee, “Classification of texture using Gaussian Markov random fields,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-33, pp. 959–963, Aug. 1985.
[25]F. S. Cohen, Z. Fan, and M. A. Patel, “Classification of rotated and Scaled texture images using Gaussian Markov random fields,” IEEE Trans. Pattern Anal. Machine Intell., vol. 13, pp. 192–203, Feb. 1991.
[26]R. L. Kashyap and R. Chellappa, “Estimation and choice of Neighbors in spatial-interaction models of images,” IEEE Trans. Inform. Theory, vol. 29, no. 1, pp. 61–72, 1983.
[27]B. Yue, “SAR sea ice recognition using texture methods,” Master’s thesis, Univ. Waterloo, Waterloo, ON, Canada, 2001.
[28]P.W. Huang and S.K. Dai, “Image Retrieval by Texture Similarity,”accepted by Pattern Recognition, March 29, 2002 .
[29]周鵬程，「遺傳演算法原理與應用」，全華科技圖書股份有限公司，民國91 年10 月。
[30]Z. Michalewicz and M. Schoenauer, “Evolutionary algorithms for constrained parameter optimization problems,” Evolutionary Computation, vol.4, no.1, pp.1-32, 1996.
[31]R. O. Stehling, M. A. Nascimento, and A. X. Falcao (2001), “An Adaptive and Efficient Clustering-Based Approach for Content- Based Image Retrieval in Image Databases,” International Symposium on Database Engineering & Application, Grenoble, France, Vol. 1, pp. 356-365.